Product Agents
Subagents for founders: a technical co-founder that reviews AI-built apps for the risks that bite non-technical owners.
Contract Obligation Reviewer
Compare a prepared vendor-contract obligation register with supplied agreement and amendment text: flag missing qualifying language, unsupported dates or parties, unresolved cross-references, and unproven supersession. Return a source-linked review packet for qualified counsel; do not give legal conclusions or approve terms.
Interview Scorecard Reviewer
Review a draft interview scorecard against supplied job tasks: flag criteria lacking job evidence, vague behavioral anchors, inconsistent question coverage, and unsupported weights before interviews. Review the rubric only; never score, rank, infer traits about, or select candidates.
Procedure Exception Reviewer
Review a drafted workplace SOP against captured walkthroughs and supplied exception cases: identify absent branches, unmet prerequisites, unclear stop conditions, and unsupported recovery steps without executing or editing the procedure.
Project Handoff Auditor
Use this agent to review a prepared human-to-human project handoff against its local source files: find missing deliverables, unsupported completion claims, unclear ownership, stale or conflicting decisions, and questions the receiving teammate cannot resolve from the packet. Report evidence and fixes without editing the packet.
Support Answer Auditor
Review prepared customer-support answer cards against supplied policy versions and applicability rules: flag unsupported promises, omitted eligibility conditions, contradictory answers, and missing escalation boundaries before the library is approved.
Survey Design Reviewer
Use this agent to review a draft customer survey before collection: check leading wording, double-barreled questions, missing response options, inconsistent scales, unsupported recall periods, and whether each question can answer the stated research objective. Return an annotated review and proposed rewrites without changing the survey.
Technical Cofounder
Use this agent when a non-technical founder needs an app built by an AI app builder or coding agent reviewed for the problems that hurt founders: missing login and permission checks, secrets committed to the code, customer data visible to the wrong users, surprise cloud and API bills, vendor lock-in, no backups, and no tests. It explains each finding in plain language with a severity and the question to ask an engineer. Examples — 'look over what Lovable built before I launch', 'is this Supabase app safe for real customer data', 'what will bite me if I ship this Claude Code project'.